postfix-2.11-20130928

postfix/HISTORY

@@ -18943,3 +18943,14 @@ Apologies for any names omitted.
 	util/dict_open.c, util/dict_alloc.c, util/dict_lmdb.c,
 	postmap/postmap.c, postalias/postalias.c, proto/LMDB_README.html,
 	proto/postconf.proto.
+
+20130928
+
+	Cleanup: the lmdb_max_readers property is now configurable.
+	This is a hard limit built into the OpenLDAP library that
+	causes requests to fail when the number of open read
+	transactions exceeds the limit.  When this happens the LMDB
+	client logs a MDB_READERS_FULL warning and continues with
+	reduced performance.  Files: util/dict_lmdb.c, util/dict_lmdb.h,
+	global/mail_params.h, global/mail_params.c, proto/postconf.proto,
+	proto/LMDB_README.html.

postfix/README_FILES/LMDB_README

@@ -39,13 +39,19 @@ The exact pathnames depend on how OpenLDAP LMDB was installed.
 
 CCoonnffiigguurree LLMMDDBB sseettttiinnggss
 
-Postfix provides one configuration parameter that controls OpenLDAP LMDB
+Postfix provides configuration parameters that control OpenLDAP LMDB database
-database behavior.
+behavior.
 
   * lmdb_map_size (default: 16777216). This setting specifies the initial
     OpenLDAP LMDB database size limit in bytes. Each time a database becomes
     full, its size limit is doubled.
 
+  * lmdb_max_readers (default: $default_process_limit). This specifies a hard
+    limit on the number of read transactions that may be open at the same time
+    for the same OpenLDAP LMDB database. When this number is too small, the
+    Postfix LMDB client will log MDB_READERS_FULL warnings, and will run with
+    reduced performance.
+
 MMiissssiinngg pptthhrreeaadd lliibbrraarryy ttrroouubbllee
 
 When building Postfix fails with:
@@ -68,6 +74,26 @@ that don't exist with other Postfix databases. Some failure modes have been
 eliminated on the course of time. The writeup below reflects the status as of
 of LMDB 0.9.8.
 
+UUnneexxppeecctteedd ""rreeaaddeerrss ffuullll"" eerrrroorrss..
+
+Problem:
+    Under heavy load, database read operations fail with MDB_READERS_FULL
+    errors. This problem does not exist with other Postfix databases.
+
+Background:
+    The LMDB implementation enforces a hard limit on the number of simultaneous
+    read requests for the same database environment. This limit must be
+    specified with the lmdb_max_readers configuration parameter.
+
+Mitigation:
+    Postfix logs a warning suggesting that the lmdb_max_readers parameter value
+    be increased, and retries the failed operation for a limited number of
+    times while running with reduced performance.
+
+Prevention:
+    Monitor your LMDB files for MDB_READERS_FULL errors and make the necessary
+    adjustments. Consider using CDB for read-mostly databases.
+
 NNoonn--oobbvviioouuss rreeccoovveerryy wwiitthh ppoossttmmaapp((11))//ppoossttaalliiaass((11))//ttllssmmggrr((88)) ffrroomm aa ccoorrrruupptteedd
 ddaattaabbaassee..
 

postfix/html/LMDB_README.html

@@ -69,7 +69,7 @@ build Postfix with OpenLDAP LMDB support, use something like: </p>
 
 <h2><a name="configure">Configure LMDB settings</a></h2>
 
-<p> Postfix provides one configuration parameter that controls 
+<p> Postfix provides configuration parameters that control 
 OpenLDAP LMDB database behavior. </p>
 
 <ul>
@@ -78,6 +78,13 @@ OpenLDAP LMDB database behavior. </p>
 the initial OpenLDAP LMDB database size limit in bytes.  Each time
 a database becomes full, its size limit is doubled.  </p>
 
+<li> <p> <a href="postconf.5.html#lmdb_max_readers">lmdb_max_readers</a> (default: $<a href="postconf.5.html#default_process_limit">default_process_limit</a>). This
+specifies a hard limit on the number of read transactions that may
+be open at the same time for the same OpenLDAP LMDB database. When
+this number is too small, the Postfix LMDB client will log
+MDB_READERS_FULL warnings, and will run with reduced performance.
+</p>
+
 </ul>
 
 <h2><a name="pthread">Missing pthread library trouble</a></h2>
@@ -113,6 +120,28 @@ failure modes that don't exist with other Postfix databases.  Some
 failure modes have been eliminated on the course of time.
 The writeup below reflects the status as of of LMDB 0.9.8. </p>
 
+<p> <strong>Unexpected "readers full" errors. </strong></p>
+
+<dl>
+
+<dt> Problem: </dt> <dd> <p> Under heavy load, database read
+operations fail with MDB_READERS_FULL errors. This problem does not
+exist with other Postfix databases. </p> </dd>
+
+<dt> Background: </dt> <dd> <p> The LMDB implementation enforces a
+hard limit on the number of simultaneous read requests for the same
+database environment. This limit must be specified with the
+<a href="postconf.5.html#lmdb_max_readers">lmdb_max_readers</a> configuration parameter. </p> </dd>
+
+<dt> Mitigation: </dt> <dd> <p> Postfix logs a warning suggesting
+that the <a href="postconf.5.html#lmdb_max_readers">lmdb_max_readers</a> parameter value be increased, and retries
+the failed operation for a limited number of times while running
+with reduced performance.  </p> </dd>
+
+<dt> Prevention: </dt> <dd> <p> Monitor your LMDB files for
+MDB_READERS_FULL errors and make the necessary adjustments.
+Consider using CDB for read-mostly databases.  </p> </dd> </dl>
+
 <!--
 
 <p> <strong>Unexpected <a href="postmap.1.html">postmap(1)</a>/<a href="postalias.1.html">postalias(1)</a> "database full"

postfix/html/oqmgr.8.html

@@ -292,8 +292,9 @@ OQMGR(8)                                                              OQMGR(8)
               deferred message.
 
        <b><a href="postconf.5.html#maximal_queue_lifetime">maximal_queue_lifetime</a> (5d)</b>
-              The maximal time a message is queued before  it  is
+              Consider a message as undeliverable, when  delivery
-              sent back as undeliverable.
+              fails  with  a temporary error, and the time in the
+              queue has reached the <a href="postconf.5.html#maximal_queue_lifetime">maximal_queue_lifetime</a> limit.
 
        <b><a href="postconf.5.html#queue_run_delay">queue_run_delay</a> (300s)</b>
               The  time between <a href="QSHAPE_README.html#deferred_queue">deferred queue</a> scans by the queue
@@ -308,8 +309,10 @@ OQMGR(8)                                                              OQMGR(8)
        Available in Postfix version 2.1 and later:
 
        <b><a href="postconf.5.html#bounce_queue_lifetime">bounce_queue_lifetime</a> (5d)</b>
-              The  maximal time a bounce message is queued before
+              Consider  a  bounce  message as undeliverable, when
-              it is considered undeliverable.
+              delivery fails with a temporary error, and the time
+              in  the queue has reached the <a href="postconf.5.html#bounce_queue_lifetime">bounce_queue_lifetime</a>
+              limit.
 
        Available in Postfix version 2.5 and later:
 

postfix/html/postconf.5.html

@@ -3794,6 +3794,18 @@ This feature is available in Postfix 2.11 and later.
 </p>
 
 
+</DD>
+
+<DT><b><a name="lmdb_max_readers">lmdb_max_readers</a>
+(default: $<a href="postconf.5.html#default_process_limit">default_process_limit</a>)</b></DT><DD>
+
+<p> The hard limit on the number of read transactions that may be
+open at the same time for the same OpenLDAP LMDB database.  When
+this number is too small, the Postfix LMDB client will log
+MDB_READERS_FULL errors, and will run with reduced performance.
+</p>
+
+
 </DD>
 
 <DT><b><a name="lmtp_address_preference">lmtp_address_preference</a>

postfix/html/qmgr.8.html

@@ -364,8 +364,9 @@ QMGR(8)                                                                QMGR(8)
               deferred message.
 
        <b><a href="postconf.5.html#maximal_queue_lifetime">maximal_queue_lifetime</a> (5d)</b>
-              The maximal time a message is queued before  it  is
+              Consider a message as undeliverable, when  delivery
-              sent back as undeliverable.
+              fails  with  a temporary error, and the time in the
+              queue has reached the <a href="postconf.5.html#maximal_queue_lifetime">maximal_queue_lifetime</a> limit.
 
        <b><a href="postconf.5.html#queue_run_delay">queue_run_delay</a> (300s)</b>
               The  time between <a href="QSHAPE_README.html#deferred_queue">deferred queue</a> scans by the queue
@@ -380,8 +381,10 @@ QMGR(8)                                                                QMGR(8)
        Available in Postfix version 2.1 and later:
 
        <b><a href="postconf.5.html#bounce_queue_lifetime">bounce_queue_lifetime</a> (5d)</b>
-              The  maximal time a bounce message is queued before
+              Consider  a  bounce  message as undeliverable, when
-              it is considered undeliverable.
+              delivery fails with a temporary error, and the time
+              in  the queue has reached the <a href="postconf.5.html#bounce_queue_lifetime">bounce_queue_lifetime</a>
+              limit.
 
        Available in Postfix version 2.5 and later:
 

postfix/man/man5/postconf.5

@@ -2247,6 +2247,11 @@ The initial OpenLDAP LMDB database size limit in bytes.  Each time
 a database becomes full, its size limit is doubled.
 .PP
 This feature is available in Postfix 2.11 and later.
+.SH lmdb_max_readers (default: $default_process_limit)
+The hard limit on the number of read transactions that may be
+open at the same time for the same OpenLDAP LMDB database.  When
+this number is too small, the Postfix LMDB client will log
+MDB_READERS_FULL errors, and will run with reduced performance.
 .SH lmtp_address_preference (default: ipv6)
 The LMTP-specific version of the smtp_address_preference
 configuration parameter.  See there for details.

postfix/man/man8/oqmgr.8

@@ -266,8 +266,9 @@ prior to Postfix 2.4 the default value was 1000s.
 .IP "\fBmaximal_backoff_time (4000s)\fR"
 The maximal time between attempts to deliver a deferred message.
 .IP "\fBmaximal_queue_lifetime (5d)\fR"
-The maximal time a message is queued before it is sent back as
+Consider a message as undeliverable, when delivery fails with a
-undeliverable.
+temporary error, and the time in the queue has reached the
+maximal_queue_lifetime limit.
 .IP "\fBqueue_run_delay (300s)\fR"
 The time between deferred queue scans by the queue manager;
 prior to Postfix 2.4 the default value was 1000s.
@@ -277,8 +278,9 @@ a malfunctioning message delivery transport.
 .PP
 Available in Postfix version 2.1 and later:
 .IP "\fBbounce_queue_lifetime (5d)\fR"
-The maximal time a bounce message is queued before it is considered
+Consider a bounce message as undeliverable, when delivery fails
-undeliverable.
+with a temporary error, and the time in the queue has reached the
+bounce_queue_lifetime limit.
 .PP
 Available in Postfix version 2.5 and later:
 .IP "\fBdefault_destination_rate_delay (0s)\fR"

postfix/man/man8/qmgr.8

@@ -314,8 +314,9 @@ prior to Postfix 2.4 the default value was 1000s.
 .IP "\fBmaximal_backoff_time (4000s)\fR"
 The maximal time between attempts to deliver a deferred message.
 .IP "\fBmaximal_queue_lifetime (5d)\fR"
-The maximal time a message is queued before it is sent back as
+Consider a message as undeliverable, when delivery fails with a
-undeliverable.
+temporary error, and the time in the queue has reached the
+maximal_queue_lifetime limit.
 .IP "\fBqueue_run_delay (300s)\fR"
 The time between deferred queue scans by the queue manager;
 prior to Postfix 2.4 the default value was 1000s.
@@ -325,8 +326,9 @@ a malfunctioning message delivery transport.
 .PP
 Available in Postfix version 2.1 and later:
 .IP "\fBbounce_queue_lifetime (5d)\fR"
-The maximal time a bounce message is queued before it is considered
+Consider a bounce message as undeliverable, when delivery fails
-undeliverable.
+with a temporary error, and the time in the queue has reached the
+bounce_queue_lifetime limit.
 .PP
 Available in Postfix version 2.5 and later:
 .IP "\fBdefault_destination_rate_delay (0s)\fR"

postfix/mantools/postlink

@@ -209,6 +209,7 @@ while (<>) {
     s;\bipc_ttl\b;<a href="postconf.5.html#ipc_ttl">$&</a>;g;
     s;\bline_length_limit\b;<a href="postconf.5.html#line_length_limit">$&</a>;g;
     s;\blmdb_map_size\b;<a href="postconf.5.html#lmdb_map_size">$&</a>;g;
+    s;\blmdb_max_readers\b;<a href="postconf.5.html#lmdb_max_readers">$&</a>;g;
     s;\blmtp_address_preference\b;<a href="postconf.5.html#lmtp_address_preference">$&</a>;g;
     s;\blmtp_body_checks\b;<a href="postconf.5.html#lmtp_body_checks">$&</a>;g;
     s;\blmtp_cname_overrides_servername\b;<a href="postconf.5.html#lmtp_cname_overrides_servername">$&</a>;g;

postfix/proto/LMDB_README.html

@@ -69,7 +69,7 @@ build Postfix with OpenLDAP LMDB support, use something like: </p>
 
 <h2><a name="configure">Configure LMDB settings</a></h2>
 
-<p> Postfix provides one configuration parameter that controls 
+<p> Postfix provides configuration parameters that control 
 OpenLDAP LMDB database behavior. </p>
 
 <ul>
@@ -78,6 +78,13 @@ OpenLDAP LMDB database behavior. </p>
 the initial OpenLDAP LMDB database size limit in bytes.  Each time
 a database becomes full, its size limit is doubled.  </p>
 
+<li> <p> lmdb_max_readers (default: $default_process_limit). This
+specifies a hard limit on the number of read transactions that may
+be open at the same time for the same OpenLDAP LMDB database. When
+this number is too small, the Postfix LMDB client will log
+MDB_READERS_FULL warnings, and will run with reduced performance.
+</p>
+
 </ul>
 
 <h2><a name="pthread">Missing pthread library trouble</a></h2>
@@ -113,6 +120,28 @@ failure modes that don't exist with other Postfix databases.  Some
 failure modes have been eliminated on the course of time.
 The writeup below reflects the status as of of LMDB 0.9.8. </p>
 
+<p> <strong>Unexpected "readers full" errors. </strong></p>
+
+<dl>
+
+<dt> Problem: </dt> <dd> <p> Under heavy load, database read
+operations fail with MDB_READERS_FULL errors. This problem does not
+exist with other Postfix databases. </p> </dd>
+
+<dt> Background: </dt> <dd> <p> The LMDB implementation enforces a
+hard limit on the number of simultaneous read requests for the same
+database environment. This limit must be specified with the
+lmdb_max_readers configuration parameter. </p> </dd>
+
+<dt> Mitigation: </dt> <dd> <p> Postfix logs a warning suggesting
+that the lmdb_max_readers parameter value be increased, and retries
+the failed operation for a limited number of times while running
+with reduced performance.  </p> </dd>
+
+<dt> Prevention: </dt> <dd> <p> Monitor your LMDB files for
+MDB_READERS_FULL errors and make the necessary adjustments.
+Consider using CDB for read-mostly databases.  </p> </dd> </dl>
+
 <!--
 
 <p> <strong>Unexpected postmap(1)/postalias(1) "database full"

postfix/proto/postconf.proto

@@ -2848,6 +2848,15 @@ a database becomes full, its size limit is doubled.
 This feature is available in Postfix 2.11 and later.
 </p>
 
+%PARAM lmdb_max_readers $default_process_limit
+
+<p> The hard limit on the number of read transactions that may be
+open at the same time for the same OpenLDAP LMDB database.  When
+this number is too small, the Postfix LMDB client will log
+MDB_READERS_FULL errors, and will run with reduced performance.
+</p>
+
+
 %PARAM message_size_limit 10240000
 
 <p>

postfix/src/global/mail_params.c

@@ -97,6 +97,8 @@
 /*	int	var_db_create_buf;
 /*	int	var_db_read_buf;
 /*	long	var_lmdb_map_size;
+/*	int	var_proc_limit;
+/*	int	var_lmdb_max_readers;
 /*	int	var_mime_maxdepth;
 /*	int	var_mime_bound_len;
 /*	int	var_header_limit;
@@ -289,6 +291,8 @@ char   *var_proxywrite_service;
 int     var_db_create_buf;
 int     var_db_read_buf;
 long    var_lmdb_map_size;
+int     var_lmdb_max_readers;
+int     var_proc_limit;
 int     var_mime_maxdepth;
 int     var_mime_bound_len;
 int     var_header_limit;
@@ -591,6 +595,7 @@ void    mail_params_init()
 	0,
     };
     static const CONFIG_INT_TABLE other_int_defaults[] = {
+	VAR_PROC_LIMIT, DEF_PROC_LIMIT, &var_proc_limit, 1, 0,
 	VAR_MAX_USE, DEF_MAX_USE, &var_use_limit, 1, 0,
 	VAR_DONT_REMOVE, DEF_DONT_REMOVE, &var_dont_remove, 0, 0,
 	VAR_LINE_LIMIT, DEF_LINE_LIMIT, &var_line_limit, 512, 0,
@@ -609,9 +614,13 @@ void    mail_params_init()
 	VAR_INET_WINDOW, DEF_INET_WINDOW, &var_inet_windowsize, 0, 0,
 	0,
     };
+    static const CONFIG_NINT_TABLE nint_defaults[] = {
+	VAR_LMDB_MAX_READERS, DEF_LMDB_MAX_READERS, &var_lmdb_max_readers, 1, 0,
+	0,
+    };
     static const CONFIG_LONG_TABLE long_defaults[] = {
 	VAR_MESSAGE_LIMIT, DEF_MESSAGE_LIMIT, &var_message_limit, 0, 0,
-	VAR_LMDB_MAP_SIZE, DEF_LMDB_MAP_SIZE, &var_lmdb_map_size, 1, 0,
+	VAR_LMDB_MAP_SIZE, DEF_LMDB_MAP_SIZE, &var_lmdb_map_size, 8192, 0,
 	0,
     };
     static const CONFIG_TIME_TABLE time_defaults[] = {
@@ -709,6 +718,7 @@ void    mail_params_init()
     }
 #endif
     get_mail_conf_int_table(other_int_defaults);
+    get_mail_conf_nint_table(nint_defaults);
     get_mail_conf_long_table(long_defaults);
     get_mail_conf_bool_table(bool_defaults);
     get_mail_conf_time_table(time_defaults);
@@ -721,6 +731,7 @@ void    mail_params_init()
 #endif
 #ifdef HAS_LMDB
     dict_lmdb_map_size = var_lmdb_map_size;
+    dict_lmdb_max_readers = var_lmdb_max_readers;
 #endif
     inet_windowsize = var_inet_windowsize;
 

postfix/src/global/mail_params.h

@@ -2769,12 +2769,16 @@ extern int var_db_create_buf;
 extern int var_db_read_buf;
 
  /*
-  * OpenLDAP LMDB memory map size.
+  * OpenLDAP LMDB settings.
   */
 #define VAR_LMDB_MAP_SIZE		"lmdb_map_size"
 #define DEF_LMDB_MAP_SIZE		(16 * 1024 *1024)
 extern long var_lmdb_map_size;
 
+#define VAR_LMDB_MAX_READERS		"lmdb_max_readers"
+#define DEF_LMDB_MAX_READERS		"$" VAR_PROC_LIMIT
+extern int var_lmdb_max_readers;
+
  /*
   * Named queue file attributes.
   */

postfix/src/global/mail_version.h

@@ -20,7 +20,7 @@
   * Patches change both the patchlevel and the release date. Snapshots have no
   * patchlevel; they change the release date only.
   */
-#define MAIL_RELEASE_DATE	"20130927"
+#define MAIL_RELEASE_DATE	"20130928"
 #define MAIL_VERSION_NUMBER	"2.11"
 
 #ifdef SNAPSHOT

postfix/src/global/mkmap_lmdb.c

@@ -61,53 +61,11 @@
 
 #include "mkmap.h"
 
-int     var_proc_limit;
-
 /* mkmap_lmdb_open */
 
 MKMAP  *mkmap_lmdb_open(const char *path)
 {
     MKMAP  *mkmap = (MKMAP *) mymalloc(sizeof(*mkmap));
-    static const CONFIG_INT_TABLE int_table[] = {
-	VAR_PROC_LIMIT, DEF_PROC_LIMIT, &var_proc_limit, 1, 0,
-	0,
-    };
-
-    get_mail_conf_int_table(int_table);
-
-    /*
-     * XXX Why is this not set in mail_params.c (with proper #ifdefs)?
-     * 
-     * Override the default per-table map size for map (re)builds.
-     * 
-     * lmdb_map_size is defined in util/dict_lmdb.c and defaults to 10MB. It
-     * needs to be large enough to contain the largest tables in use.
-     * 
-     * XXX This should be specified via the DICT interface so that the buffer
-     * size becomes an object property, instead of being specified by poking
-     * a global variable so that it becomes a class property.
-     * 
-     * XXX Wietse disagrees: storage infrastructure that requires up-front
-     * max-size information is evil. This unlike Postfix (e.g. line length or
-     * process count) limits which are a defense against out-of-control or
-     * malicious external actors.
-     * 
-     * XXX Need to check that an existing table can be rebuilt with a larger
-     * size limit than was used for the initial build.
-     */
-    dict_lmdb_map_size = var_lmdb_map_size;
-
-    /*
-     * XXX Why is this not set in mail_params.c (with proper #ifdefs)?
-     * 
-     * Set the max number of concurrent readers per table. This is the
-     * maximum number of postfix processes, plus some extra for CLI users.
-     * 
-     * XXX Postfix uses asynchronous or blocking I/O with single-threaded
-     * processes so this limit will never be reached, assuming that the limit
-     * is a per-client property, not a shared database property.
-     */
-    dict_lmdb_max_readers = var_proc_limit * 2 + 16;
 
     /*
      * Fill in the generic members.

postfix/src/master/master_vars.c

@@ -47,7 +47,6 @@
   * Tunable parameters.
   */
 char   *var_inet_protocols;
-int     var_proc_limit;
 int     var_throttle_time;
 char   *var_master_disable;
 
@@ -60,10 +59,6 @@ void    master_vars_init(void)
 	VAR_MASTER_DISABLE, DEF_MASTER_DISABLE, &var_master_disable, 0, 0,
 	0,
     };
-    static const CONFIG_INT_TABLE int_table[] = {
-	VAR_PROC_LIMIT, DEF_PROC_LIMIT, &var_proc_limit, 1, 0,
-	0,
-    };
     static const CONFIG_TIME_TABLE time_table[] = {
 	VAR_THROTTLE_TIME, DEF_THROTTLE_TIME, &var_throttle_time, 1, 0,
 	0,
@@ -87,7 +82,6 @@ void    master_vars_init(void)
     set_mail_conf_str(VAR_PROCNAME, var_procname);
     mail_conf_read();
     get_mail_conf_str_table(str_table);
-    get_mail_conf_int_table(int_table);
     get_mail_conf_time_table(time_table);
     path = concatenate(var_config_dir, "/", MASTER_CONF_FILE, (char *) 0);
     fset_master_ent(path);

postfix/src/oqmgr/qmgr.c

@@ -232,8 +232,9 @@
 /* .IP "\fBmaximal_backoff_time (4000s)\fR"
 /*	The maximal time between attempts to deliver a deferred message.
 /* .IP "\fBmaximal_queue_lifetime (5d)\fR"
-/*	The maximal time a message is queued before it is sent back as
+/*	Consider a message as undeliverable, when delivery fails with a
-/*	undeliverable.
+/*	temporary error, and the time in the queue has reached the
+/*	maximal_queue_lifetime limit.
 /* .IP "\fBqueue_run_delay (300s)\fR"
 /*	The time between deferred queue scans by the queue manager;
 /*	prior to Postfix 2.4 the default value was 1000s.
@@ -243,8 +244,9 @@
 /* .PP
 /*	Available in Postfix version 2.1 and later:
 /* .IP "\fBbounce_queue_lifetime (5d)\fR"
-/*	The maximal time a bounce message is queued before it is considered
+/*	Consider a bounce message as undeliverable, when delivery fails
-/*	undeliverable.
+/*	with a temporary error, and the time in the queue has reached the
+/*	bounce_queue_lifetime limit.
 /* .PP
 /*	Available in Postfix version 2.5 and later:
 /* .IP "\fBdefault_destination_rate_delay (0s)\fR"
@@ -373,7 +375,6 @@ char   *var_defer_xports;
 int     var_qmgr_fudge;
 int     var_local_rcpt_lim;		/* XXX */
 int     var_local_con_lim;		/* XXX */
-int     var_proc_limit;
 bool    var_verp_bounce_off;
 int     var_qmgr_clog_warn_time;
 char   *var_conc_pos_feedback;
@@ -641,7 +642,6 @@ int     main(int argc, char **argv)
 	VAR_QMGR_FUDGE, DEF_QMGR_FUDGE, &var_qmgr_fudge, 10, 100,
 	VAR_LOCAL_RCPT_LIMIT, DEF_LOCAL_RCPT_LIMIT, &var_local_rcpt_lim, 0, 0,
 	VAR_LOCAL_CON_LIMIT, DEF_LOCAL_CON_LIMIT, &var_local_con_lim, 0, 0,
-	VAR_PROC_LIMIT, DEF_PROC_LIMIT, &var_proc_limit, 1, 0,
 	VAR_CONC_COHORT_LIM, DEF_CONC_COHORT_LIM, &var_conc_cohort_limit, 0, 0,
 	0,
     };

postfix/src/postscreen/postscreen.c

@@ -424,7 +424,6 @@
  /*
   * Configuration parameters.
   */
-int     var_proc_limit;
 char   *var_smtpd_service;
 char   *var_smtpd_banner;
 bool    var_disable_vrfy_cmd;
@@ -1100,7 +1099,6 @@ int     main(int argc, char **argv)
 	0,
     };
     static const CONFIG_INT_TABLE int_table[] = {
-	VAR_PROC_LIMIT, DEF_PROC_LIMIT, &var_proc_limit, 1, 0,
 	VAR_PSC_DNSBL_THRESH, DEF_PSC_DNSBL_THRESH, &var_psc_dnsbl_thresh, 0, 0,
 	VAR_PSC_DNSBL_WTHRESH, DEF_PSC_DNSBL_WTHRESH, &var_psc_dnsbl_wthresh, 0, 0,
 	VAR_PSC_CMD_COUNT, DEF_PSC_CMD_COUNT, &var_psc_cmd_count, 1, 0,

postfix/src/qmgr/qmgr.c

@@ -278,8 +278,9 @@
 /* .IP "\fBmaximal_backoff_time (4000s)\fR"
 /*	The maximal time between attempts to deliver a deferred message.
 /* .IP "\fBmaximal_queue_lifetime (5d)\fR"
-/*	The maximal time a message is queued before it is sent back as
+/*	Consider a message as undeliverable, when delivery fails with a
-/*	undeliverable.
+/*	temporary error, and the time in the queue has reached the
+/*	maximal_queue_lifetime limit.
 /* .IP "\fBqueue_run_delay (300s)\fR"
 /*	The time between deferred queue scans by the queue manager;
 /*	prior to Postfix 2.4 the default value was 1000s.
@@ -289,8 +290,9 @@
 /* .PP
 /*	Available in Postfix version 2.1 and later:
 /* .IP "\fBbounce_queue_lifetime (5d)\fR"
-/*	The maximal time a bounce message is queued before it is considered
+/*	Consider a bounce message as undeliverable, when delivery fails
-/*	undeliverable.
+/*	with a temporary error, and the time in the queue has reached the
+/*	bounce_queue_lifetime limit.
 /* .PP
 /*	Available in Postfix version 2.5 and later:
 /* .IP "\fBdefault_destination_rate_delay (0s)\fR"
@@ -433,7 +435,6 @@ int     var_dest_rcpt_limit;
 char   *var_defer_xports;
 int     var_local_con_lim;
 int     var_local_rcpt_lim;
-int     var_proc_limit;
 bool    var_verp_bounce_off;
 int     var_qmgr_clog_warn_time;
 char   *var_conc_pos_feedback;
@@ -716,7 +717,6 @@ int     main(int argc, char **argv)
 	VAR_DEST_RCPT_LIMIT, DEF_DEST_RCPT_LIMIT, &var_dest_rcpt_limit, 0, 0,
 	VAR_LOCAL_RCPT_LIMIT, DEF_LOCAL_RCPT_LIMIT, &var_local_rcpt_lim, 0, 0,
 	VAR_LOCAL_CON_LIMIT, DEF_LOCAL_CON_LIMIT, &var_local_con_lim, 0, 0,
-	VAR_PROC_LIMIT, DEF_PROC_LIMIT, &var_proc_limit, 1, 0,
 	VAR_CONC_COHORT_LIM, DEF_CONC_COHORT_LIM, &var_conc_cohort_limit, 0, 0,
 	0,
     };

postfix/src/util/dict_lmdb.c

@@ -7,6 +7,7 @@
 /*	#include <dict_lmdb.h>
 /*
 /*	size_t	dict_lmdb_map_size;
+/*	unsigned int dict_lmdb_max_readers;
 /*
 /*	DICT	*dict_lmdb_open(path, open_flags, dict_flags)
 /*	const char *name;
@@ -21,6 +22,11 @@
 /*	The dict_lmdb_map_size variable specifies the initial
 /*	database memory map size.  When a map becomes full its size
 /*	is doubled, and other programs pick up the size change.
+/*
+/*	The dict_lmdb_max_readers variable specifies the hard (ugh)
+/*	limit on the number of read transactions that may be open
+/*	at the same time. This should be propertional to the number
+/*	of processes that read the table.
 /* DIAGNOSTICS
 /*	Fatal errors: cannot open file, file write error, out of
 /*	memory.
@@ -97,8 +103,9 @@ typedef struct {
     /* The following facilitate LMDB quirk workarounds. */
     int     dict_api_retries;		/* workarounds per dict(3) call */
     int     bulk_mode_retries;		/* workarounds per bulk transaction */
-    int     open_flags;			/* dict(3) open flags */
+    int     dict_open_flags;		/* dict(3) open flags */
-    int     env_flags;			/* LMDB open flags */
+    int     mdb_open_flags;		/* LMDB open flags */
+    int     readers_full;		/* MDB_READERS_FULL errors */
 } DICT_LMDB;
 
  /*
@@ -130,7 +137,7 @@ typedef struct {
 #define DICT_LMDB_SIZE_INCR	2	/* Increase size by 1 bit on retry */
 #define DICT_LMDB_SIZE_MAX	SSIZE_T_MAX
 
-#define DICT_LMDB_API_RETRY_LIMIT 2	/* Retries per dict(3) API call */
+#define DICT_LMDB_API_RETRY_LIMIT 100	/* Retries per dict(3) API call */
 #define DICT_LMDB_BULK_RETRY_LIMIT \
 	(2 * sizeof(size_t) * CHAR_BIT)	/* Retries per bulk-mode transaction */
 
@@ -146,8 +153,9 @@ unsigned int dict_lmdb_max_readers = 216;	/* 200 postfix processes,
 
  /*
   * The purpose of the error-recovering functions below is to hide LMDB
-  * quirks (MAP_FULL, MAP_CHANGED), so that the dict(3) API routines can
+  * quirks (MAP_FULL, MAP_CHANGED, READERS_FULL), so that the dict(3) API
-  * pretend that those quirks don't exist, and focus on their own job.
+  * routines can pretend that those quirks don't exist, and focus on their
+  * own job.
   * 
   * - To recover from a single-transaction LMDB error, each wrapper function
   * uses tail recursion instead of goto. Since LMDB errors are rare, code
@@ -175,7 +183,7 @@ static void dict_lmdb_prepare(DICT_LMDB *dict_lmdb)
      * - With DICT_FLAG_BULK_UPDATE we commit a bulk-mode transaction when the
      * database is closed.
      */
-    if (dict_lmdb->open_flags & O_TRUNC) {
+    if (dict_lmdb->dict_open_flags & O_TRUNC) {
 	if ((status = mdb_drop(dict_lmdb->txn, dict_lmdb->dbi, 0)) != 0)
 	    msg_fatal("truncate %s:%s: %s",
 		      dict_lmdb->dict.type, dict_lmdb->dict.name,
@@ -187,7 +195,7 @@ static void dict_lmdb_prepare(DICT_LMDB *dict_lmdb)
 			  mdb_strerror(status));
 	    dict_lmdb->txn = NULL;
 	}
-    } else if ((dict_lmdb->env_flags & MDB_RDONLY) != 0
+    } else if ((dict_lmdb->mdb_open_flags & MDB_RDONLY) != 0
 	       || (dict_lmdb->dict.flags & DICT_FLAG_BULK_UPDATE) == 0) {
 	mdb_txn_abort(dict_lmdb->txn);
 	dict_lmdb->txn = NULL;
@@ -277,6 +285,20 @@ static int dict_lmdb_recover(DICT_LMDB *dict_lmdb, int status)
 		     (unsigned long) dict_lmdb->map_size);
 	break;
 
+	/*
+	 * What is it with these built-in hard limits that cause systems to
+	 * fail when resources are needed most? When the system is under
+	 * stress it should slow down, not stop working.
+	 */
+    case MDB_READERS_FULL:
+	if (dict_lmdb->readers_full++ == 0)
+	    msg_warn("database %s:%s: %s - increase lmdb_max_readers",
+		     dict_lmdb->dict.type, dict_lmdb->dict.name,
+		     mdb_strerror(status));
+	rand_sleep(1000000, 1000000);
+	status = 0;
+	break;
+
 	/*
 	 * We can't solve this problem. The application should terminate with
 	 * a fatal run-time error and the program should be re-run later.
@@ -293,7 +315,7 @@ static int dict_lmdb_recover(DICT_LMDB *dict_lmdb, int status)
     if (dict_lmdb->txn != 0 && status == 0
      && (dict_lmdb->bulk_mode_retries += 1) <= DICT_LMDB_BULK_RETRY_LIMIT) {
 	status = mdb_txn_begin(dict_lmdb->env, NULL,
-			       dict_lmdb->env_flags & MDB_RDONLY,
+			       dict_lmdb->mdb_open_flags & MDB_RDONLY,
 			       &dict_lmdb->txn);
 	if (status != 0)
 	    msg_fatal("txn_begin %s:%s: %s",
@@ -466,9 +488,21 @@ static int dict_lmdb_cursor_get(DICT_LMDB *dict_lmdb, MDB_val *mdb_key,
      * Database lookup.
      */
     status = mdb_cursor_get(dict_lmdb->cursor, mdb_key, mdb_value, op);
-    if (status != 0 && status != MDB_NOTFOUND)
+
+    /*
+     * Handle end-of-database or other error.
+     */
+    if (status != 0) {
+	if (status == MDB_NOTFOUND) {
+	    txn = mdb_cursor_txn(dict_lmdb->cursor);
+	    mdb_cursor_close(dict_lmdb->cursor);
+	    mdb_txn_abort(txn);
+	    dict_lmdb->cursor = 0;
+	} else {
 	    if ((status = dict_lmdb_recover(dict_lmdb, status)) == 0)
 		return (dict_lmdb_cursor_get(dict_lmdb, mdb_key, mdb_value, op));
+	}
+    }
     return (status);
 }
 
@@ -735,7 +769,6 @@ static int dict_lmdb_sequence(DICT *dict, int function,
     DICT_LMDB *dict_lmdb = (DICT_LMDB *) dict;
     MDB_val mdb_key;
     MDB_val mdb_value;
-    MDB_txn *txn;
     MDB_cursor_op op;
     int     status;
 
@@ -774,14 +807,10 @@ static int dict_lmdb_sequence(DICT *dict, int function,
 	break;
 
 	/*
-	 * Destroy cursor and read transaction.
+	 * End-of-database.
 	 */
     case MDB_NOTFOUND:
 	status = 1;
-	txn = mdb_cursor_txn(dict_lmdb->cursor);
-	mdb_cursor_close(dict_lmdb->cursor);
-	mdb_txn_abort(txn);
-	dict_lmdb->cursor = 0;
 	break;
 
 	/*
@@ -845,8 +874,16 @@ DICT   *dict_lmdb_open(const char *path, int open_flags, int dict_flags)
     if ((status = mdb_env_create(&env)))
 	msg_fatal("env_create %s: %s", mdb_path, mdb_strerror(status));
 
-    if (stat(mdb_path, &st) == 0 && st.st_size > map_size)
+    if (stat(mdb_path, &st) == 0 && st.st_size > map_size) {
+	if (st.st_size / map_size < DICT_LMDB_SIZE_MAX / map_size) {
+	    map_size = (st.st_size / map_size + 1) * map_size;
+	} else {
 	    map_size = st.st_size;
+	}
+	if (msg_verbose)
+	    msg_info("using %s:%s map size %lu",
+		     DICT_TYPE_LMDB, path, (unsigned long) map_size);
+    }
     if ((status = mdb_env_set_mapsize(env, map_size)))
 	msg_fatal("env_set_mapsize %s: %s", mdb_path, mdb_strerror(status));
 
@@ -872,6 +909,9 @@ DICT   *dict_lmdb_open(const char *path, int open_flags, int dict_flags)
     if ((status = mdb_open(txn, NULL, 0, &dbi)))
 	msg_fatal("mdb_open %s: %s", mdb_path, mdb_strerror(status));
 
+    /*
+     * Bundle up.
+     */
     dict_lmdb = (DICT_LMDB *) dict_alloc(DICT_TYPE_LMDB, path, sizeof(*dict_lmdb));
     dict_lmdb->dict.lookup = dict_lmdb_lookup;
     dict_lmdb->dict.update = dict_lmdb_update;
@@ -914,9 +954,10 @@ DICT   *dict_lmdb_open(const char *path, int open_flags, int dict_flags)
     /* The following facilitate transparent error recovery. */
     dict_lmdb->dict_api_retries = 0;
     dict_lmdb->bulk_mode_retries = 0;
-    dict_lmdb->open_flags = open_flags;
+    dict_lmdb->dict_open_flags = open_flags;
-    dict_lmdb->env_flags = env_flags;
+    dict_lmdb->mdb_open_flags = env_flags;
     dict_lmdb->txn = txn;
+    dict_lmdb->readers_full = 0;
     dict_lmdb_prepare(dict_lmdb);
     if (dict_flags & DICT_FLAG_BULK_UPDATE)
 	dict_jmp_alloc(&dict_lmdb->dict);	/* build into dict_alloc() */